© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 2868
    Prev
    Next
    INDEX
    Explanations

    monetary values or significant characters in narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     agency
    -0.36
     attained
    -0.34
     lanterna
    -0.34
     beard
    -0.34
    Kommentare
    -0.33
    itext
    -0.33
     Barber
    -0.32
    KindOfClass
    -0.32
    者は
    -0.32
     employer
    -0.32
    POSITIVE LOGITS
     &___
    0.92
    RegressionTest
    0.78
    jsii
    0.65
    SharedDtor
    0.65
    دانشنامهٔ
    0.63
     estekak
    0.63
     kasarigan
    0.62
     surla
    0.61
    GEBURTSDATUM
    0.60
     Roskov
    0.60
    Activations Density 0.000%

    No Known Activations